open-llm-leaderboard-old/details_ConvexAI__Solutus-3x7B
收藏Hugging Face2024-02-03 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_ConvexAI__Solutus-3x7B
下载链接
链接失效反馈官方服务:
资源简介:
该数据集是在评估模型ConvexAI/Solutus-3x7B时自动创建的,主要用于在Open LLM Leaderboard上展示模型的评估结果。数据集包含63个配置,每个配置对应一个评估任务。数据集由1次运行生成,每次运行的结果作为特定配置中的一个分割,分割名称使用运行的时间戳。train分割始终指向最新的结果。此外,results配置存储了所有运行的聚合结果,用于计算和展示在Open LLM Leaderboard上的聚合指标。
该数据集是在评估模型ConvexAI/Solutus-3x7B时自动创建的,主要用于在Open LLM Leaderboard上展示模型的评估结果。数据集包含63个配置,每个配置对应一个评估任务。数据集由1次运行生成,每次运行的结果作为特定配置中的一个分割,分割名称使用运行的时间戳。train分割始终指向最新的结果。此外,results配置存储了所有运行的聚合结果,用于计算和展示在Open LLM Leaderboard上的聚合指标。
提供机构:
open-llm-leaderboard-old
原始信息汇总
数据集概述
数据集信息
- 名称: Evaluation run of ConvexAI/Solutus-3x7B
- 来源: 在模型 ConvexAI/Solutus-3x7B 的评估运行期间自动创建
- 目标: 用于 Open LLM Leaderboard 上的评估
数据集结构
- 配置数量: 63
- 每个配置对应: 一个评估任务
- 创建次数: 1 次运行
- 分割命名: 使用运行的时间戳
- 训练分割: 始终指向最新结果
- 额外配置: "results" 存储所有聚合结果,用于计算和显示聚合指标
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_ConvexAI__Solutus-3x7B", "harness_winogrande_5", split="train")
最新结果
- 来源: 最新结果来自 run 2024-02-03T01:55:40.169312
- 详细结果: 包含多个任务的准确率(acc)、标准化准确率(acc_norm)、误差(stderr)等指标
配置详情
-
配置名称: harness_arc_challenge_25
- 数据文件:
- 分割: 2024_02_03T01_55_40.169312
- 路径: **/details_harness|arc:challenge|25_2024-02-03T01-55-40.169312.parquet
- 分割: latest
- 路径: **/details_harness|arc:challenge|25_2024-02-03T01-55-40.169312.parquet
- 分割: 2024_02_03T01_55_40.169312
- 数据文件:
-
配置名称: harness_gsm8k_5
- 数据文件:
- 分割: 2024_02_03T01_55_40.169312
- 路径: **/details_harness|gsm8k|5_2024-02-03T01-55-40.169312.parquet
- 分割: latest
- 路径: **/details_harness|gsm8k|5_2024-02-03T01-55-40.169312.parquet
- 分割: 2024_02_03T01_55_40.169312
- 数据文件:
-
配置名称: harness_hellaswag_10
- 数据文件:
- 分割: 2024_02_03T01_55_40.169312
- 路径: **/details_harness|hellaswag|10_2024-02-03T01-55-40.169312.parquet
- 分割: latest
- 路径: **/details_harness|hellaswag|10_2024-02-03T01-55-40.169312.parquet
- 分割: 2024_02_03T01_55_40.169312
- 数据文件:
-
配置名称: harness_hendrycksTest_5
- 数据文件:
- 分割: 2024_02_03T01_55_40.169312
- 路径:
- **/details_harness|hendrycksTest-abstract_algebra|5_2024-02-03T01-55-40.169312.parquet
- **/details_harness|hendrycksTest-anatomy|5_2024-02-03T01-55-40.169312.parquet
- **/details_harness|hendrycksTest-astronomy|5_2024-02-03T01-55-40.169312.parquet
- **/details_harness|hendrycksTest-business_ethics|5_2024-02-03T01-55-40.169312.parquet
- **/details_harness|hendrycksTest-clinical_knowledge|5_2024-02-03T01-55-40.169312.parquet
- **/details_harness|hendrycksTest-college_biology|5_2024-02-03T01-55-40.169312.parquet
- **/details_harness|hendrycksTest-college_chemistry|5_2024-02-03T01-55-40.169312.parquet
- **/details_harness|hendrycksTest-college_computer_science|5_2024-02-03T01-55-40.169312.parquet
- **/details_harness|hendrycksTest-college_mathematics|5_2024-02-03T01-55-40.169312.parquet
- **/details_harness|hendrycksTest-college_medicine|5_2024-02-03T01-55-40.169312.parquet
- **/details_harness|hendrycksTest-college_physics|5_2024-02-03T01-55-40.169312.parquet
- **/details_harness|hendrycksTest-computer_security|5_2024-02-03T01-55-40.169312.parquet
- **/details_harness|hendrycksTest-conceptual_physics|5_2024-02-03T01-55-40.169312.parquet
- **/details_harness|hendrycksTest-econometrics|5_2024-02-03T01-55-40.169312.parquet
- **/details_harness|hendrycksTest-electrical_engineering|5_2024-02-03T01-55-40.169312.parquet
- **/details_harness|hendrycksTest-elementary_mathematics|5_2024-02-03T01-55-40.169312.parquet
- **/details_harness|hendrycksTest-formal_logic|5_2024-02-03T01-55-40.169312.parquet
- **/details_harness|hendrycksTest-global_facts|5_2024-02-03T01-55-40.169312.parquet
- **/details_harness|hendrycksTest-high_school_biology|5_2024-02-03T01-55-40.169312.parquet
- **/details_harness|hendrycksTest-high_school_chemistry|5_2024-02-03T01-55-40.169312.parquet
- **/details_harness|hendrycksTest-high_school_computer_science|5_2024-02-03T01-55-40.169312.parquet
- **/details_harness|hendrycksTest-high_school_european_history|5_2024-02-03T01-55-40.169312.parquet
- **/details_harness|hendrycksTest-high_school_geography|5_2024-02-03T01-55-40.169312.parquet
- **/details_harness|hendrycksTest-high_school_government_and_politics|5_2024-02-03T01-55-40.169312.parquet
- **/details_harness|hendrycksTest-high_school_macroeconomics|5_2024-02-03T01-55-40.169312.parquet
- **/details_harness|hendrycksTest-high_school_mathematics|5_2024-02-03T01-55-40.169312.parquet
- **/details_harness|hendrycksTest-high_school_microeconomics|5_2024-02-03T01-55-40.169312.parquet
- **/details_harness|hendrycksTest-high_school_physics|5_2024-02-03T01-55-40.169312.parquet
- **/details_harness|hendrycksTest-high_school_psychology|5_2024-02-03T01-55-40.169312.parquet
- **/details_harness|hendrycksTest-high_school_statistics|5_2024-02-03T01-55-40.169312.parquet
- **/details_harness|hendrycksTest-high_school_us_history|5_2024-02-03T01-55-40.169312.parquet
- **/details_harness|hendrycksTest-high_school_world_history|5_2024-02-03T01-55-40.169312.parquet
- **/details_harness|hendrycksTest-human_aging|5_2024-02-03T01-55-40.169312.parquet
- **/details_harness|hendrycksTest-human_sexuality|5_2024-02-03T01-55-40.169312.parquet
- **/details_harness|hendrycksTest-international_law|5_2024-02-03T01-55-40.169312.parquet
- **/details_harness|hendrycksTest-jurisprudence|5_2024-02-03T01-55-40.169312.parquet
- **/details_harness|hendrycksTest-logical_fallacies|5_2024-02-03T01-55-40.169312.parquet
- **/details_harness|hendrycksTest-machine_learning|5_2024-02-03T01-55-40.169312.parquet
- **/details_harness|hendrycksTest-management|5_2024-02-03T01-55-40.169312.parquet
- **/details_harness|hendrycksTest-marketing|5_2024-02-03T01-55-40.169312.parquet
- **/details_harness|hendrycksTest-medical_genetics|5_2024-02-03T01-55-40.169312.parquet
- **/details_harness|hendrycksTest-miscellaneous|5_2024-02-03T01-55-40.169312.parquet
- **/details_harness|hendrycksTest-moral_disputes|5_2024-02-03T01-55-40.169312.parquet
- **/details_harness|hendrycksTest-moral_scenarios|5_2024-02-03T01-55-40.169312.parquet
- **/details_harness|hendrycksTest-nutrition|5_2024-02-03T01-55-40.169312.parquet
- **/details_harness|hendrycksTest-philosophy|5_2024-02-03T01-55-40.169312.parquet
- **/details_harness|hendrycksTest-prehistory|5_2024-02-03T01-55-40.169312.parquet
- **/details_harness|hendrycksTest-professional_accounting|5_2024-02-03T01-55-40.169312.parquet
- **/details_harness|hendrycksTest-professional_law|5_2024-02-03T01-55-40.169312.parquet
- **/details_harness|hendrycksTest-professional_medicine|5_2024-02-03T01-55-40.169312.parquet
- **/details_harness|hendrycksTest-professional_psychology|5_2024-02-03T01-55-40.169312.parquet
- **/details_harness|hendrycksTest-public_relations|5_2024-02-03T01-55-40.169312.parquet
- **/details_harness|hendrycksTest-security_studies|5_2024-02-03T01-55-40.169312.parquet
- **/details_harness|hendrycksTest-sociology|5_2024-02-03T01-55-40.169312.parquet
- **/details_harness|hendrycksTest-us_foreign_policy|5_2024-02-03T01-55-40.169312.parquet
- **/details_harness|hendrycksTest-virology|5_2024-02-03T01-55-40.169312.parquet
- **/details_harness|hendrycksTest-world_religions|5_2024-02-03T01-55-40.169312.parquet
- 路径:
- 分割: latest
- 路径:
- **/details_harness|hendrycksTest-abstract_algebra|5_2024-02-03T01-55-40.169312.parquet
- **/details_harness|hendrycksTest-anatomy|5_2024-02-03T01-55-40.169312.parquet
- **/details_harness|hendrycksTest-astronomy|5_2024-02-03T01-55-40.1
- 路径:
- 分割: 2024_02_03T01_55_40.169312
- 数据文件:



